Efficient inference has become crucial for hyper-scale AI models, including large language models, as their parameter count continues to increase for enhanced performance. This necessity holds true regardless of the computing environment, whether it be mobile devices or cloud servers. Quantization emerges as a solution to alleviate the computational burden during inference. By representing models with a reduced bit-width, quantization minimizes the frequency of DRAM access while fully exploiting the parallelism of operations through a dense matrix format. Consequently, quantized models achieve low end-to-end latency and optimize resource utilization by addressing both memory and computing bottlenecks. In this paper, we propose a straightforward posttraining quantization scheme, called Z-FOLD, that fully utilizes the feature of the Transformer structure widely employed in large language models. The code will be available at https: //github.com/SamsungLabs/Z-Fold

https://aclanthology.org/2023.emnlp-main.892.pdf